collaborators

12 papers

cs.LG2026

Offline Reinforcement Learning for Rotation Profile Control in Tokamaks

Rohit Sonker, Hiro Josep Farre Kaga, Jiayu Chen +5

Tokamaks remain leading candidates for achieving practical fusion energy, yet many important control problems inside these devices are still difficult or unsolved. One such challen…

cs.CV2026

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation

Jiayi Luo, Qiyan Liu, Tengyang Wang +8

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens.…

cs.LG2026

Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark

Yang Fu, Haomin Bao, Rohit Sonker +4

Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly…

stat.ML2026

Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems

Haixiang, Yang Xu, Jiefu Zhang +4

We study solving large-scale fixed-point equation \(x^\star=\bar F(x^\star)\) with decomposition. Standard strict decomposition assigns each agent a disjoint block and evaluates up…

cs.AI2026

ANO: A Principled Approach to Robust Policy Optimization

Yiheng Zhang, Yiming Wang, Kaiyan Zhao +3

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, uncons…

cs.LG2026

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

Aravind Venugopal, Jiayu Chen, Xudong Wu +3

The temporal lag between actions and their long-term consequences makes credit assignment a challenge when learning goal-directed behaviors from data. Generative world models captu…